Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases that involve dialogue or quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ünchen
    -0.18
    pedia
    -0.17
    zsche
    -0.17
    won
    -0.16
    bsite
    -0.15
    alty
    -0.15
    éħ
    -0.15
    ighest
    -0.15
    egas
    -0.15
    zp
    -0.15
    POSITIVE LOGITS
     Hun
    0.14
     generic
    0.14
     Berk
    0.14
     bat
    0.14
     Birds
    0.13
     Pur
    0.13
     birds
    0.13
     Generic
    0.13
    ade
    0.13
    âĢIJ
    0.13
    Act Density 0.000%

    No Known Activations